Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
vue
Vue.js progressive JavaScript framework. Use when building Vue components, working with reactivity (ref, reactive, computed, watch), or implementing Vue Composition API patterns.
report-generation
通用的报告生成技能，根据用户诉求生成各类数据分析报告，包括数据库查询、统计分析和 HTML 图表可视化
Line Execution Checker
Check if specific lines were executed using gcov data
daily-meeting-update
Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update.
Executing Work in Parallel
This skill provides a structured framework for coordinating multiple Claude agents to work on independent tasks simultaneously. It includes clear guidelines for task analysis, dependency management, and execution patterns for layer-based development, research investigations, and multi-file refactoring.
fish-shell-config
This skill provides detailed guidance for configuring Fish shell, covering functions, aliases, variables, and scripting. It explains Fish-specific concepts like autoloading and universal variables, includes migration tips from bash, and offers practical examples for common tasks. The modular configuration approach and clear file structure recommendations help users organize their setup effectively.
building-with-dapr
Provides detailed guidance for building Dapr-based microservices, covering sidecar architecture, building blocks, actors, and workflows. Includes concrete code examples for service invocation, state management, pub/sub, and error handling. Clearly defines when to use and when to avoid this approach.
technical-clarity
This skill reviews technical documentation for accessibility issues, jargon density, and gatekeeping language. It provides structured questions and principles to ensure content is understandable to learners at different proficiency levels, with specific guidelines for sentence length, term definitions, and visual accessibility.
render-template
A template rendering tool that replaces variables in text using Mustache or shell syntax. Handles nested properties, missing values, and basic filters. Useful for generating commit messages, reports, and formatted outputs across Claude Skills.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
anti-slop
Detects and removes generic AI-generated patterns in text, code, and design. Provides detection scripts, cleanup tools, and reference guides for common slop patterns like overused phrases and generic variable names.
debug-protocol
Provides a structured 5-step debugging protocol (Reproduce, Isolate, Identify, Fix, Verify) with mandatory logging to prevent guess-and-retry loops. Enforces a 3-5-rewrite rule and includes specific checklists for CSS/JS issues and multi-AI handoff procedures.
crew-roles
Defines seven distinct roles (Creative Director, Research Analyst, etc.) for orchestrating multi-persona collaboration in Claude's Crew mode. Each role has clear responsibilities, communication patterns, and persona mappings to improve structured content generation.
software-ux-research
A structured guide for planning and executing UX research across the product lifecycle. It provides method selection frameworks, templates for research plans and reports, and specific guidance for handling PII and AI-powered features. Focuses on connecting research activities to business decisions.
claude-code-project-memory
This skill provides a reference guide for setting up and managing CLAUDE.md files, which store project context for Claude. It explains a 4-tier memory hierarchy, offers templates for architecture and standards, and includes commands for quick memory management and session handling.
frontend-design
This skill generates frontend code with strong aesthetic direction, avoiding generic AI designs. It enforces specific animation libraries (anime.js v4), provides detailed typography and color guidelines, and pushes for bold creative choices in web interfaces.
seo-geo
SEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Use when user wants to improve search visibility.
agent-evals
Provides a systematic approach to evaluating AI agents using binary criteria instead of subjective scales. Focuses on error analysis, trace examination, and creating component-level tests. Includes practical templates for graders and workflows to identify failure patterns in agent reasoning.
frontend-aesthetics
Provides specific guidance for avoiding generic AI-generated frontend aesthetics. Offers concrete font alternatives, color palette principles, and animation strategies. Outputs structured JSON with typography, color, animation, and background recommendations. Includes anti-pattern checklist and practical implementation examples.
route-tester
Test authenticated routes in the your project using cookie-based authentication. Use this skill when testing API endpoints, validating route functionality, or debugging authentication issues. Includes patterns for using test-auth-route.js and mock authentication.
Vibe Calibration Protocol
Translate consciousness navigation into user's native language. Use when need to match user's frequency (technical/poetic/practical/mystical) without losing truth depth.
cellxgene-census
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis.
ffuf-web-fuzzing
Provides detailed guidance for using ffuf web fuzzer in penetration testing, covering installation, core concepts, common use cases, filtering strategies, and troubleshooting. Includes helper scripts for result analysis and request template creation. Emphasizes auto-calibration to reduce false positives and authenticated fuzzing techniques.
pdb-database
Provides programmatic access to RCSB Protein Data Bank for structural biology workflows. Enables searching 200,000+ protein/nucleic acid structures by text, sequence, or structural similarity. Downloads coordinate files (PDB/mmCIF) and retrieves metadata for computational analysis in drug discovery and protein engineering.